New! View global litigation for patent families

US6018590A - Technique for finding the histogram region of interest based on landmark detection for improved tonescale reproduction of digital radiographic images - Google Patents

Technique for finding the histogram region of interest based on landmark detection for improved tonescale reproduction of digital radiographic images Download PDF

Info

Publication number
US6018590A
US6018590A US08946557 US94655797A US6018590A US 6018590 A US6018590 A US 6018590A US 08946557 US08946557 US 08946557 US 94655797 A US94655797 A US 94655797A US 6018590 A US6018590 A US 6018590A
Authority
US
Grant status
Grant
Patent type
Prior art keywords
image
features
region
method
interest
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Lifetime
Application number
US08946557
Inventor
Roger S. Gaborski
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Carestream Health Inc
Original Assignee
Eastman Kodak Co
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Grant date

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00Image enhancement or restoration, e.g. from bit-mapped to bit-mapped creating a similar image
    • G06T5/007Dynamic range modification
    • G06T5/009Global, i.e. based on properties of the image as a whole
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/20Image acquisition
    • G06K9/32Aligning or centering of the image pick-up or image-field
    • G06K9/3233Determination of region of interest
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00Image enhancement or restoration, e.g. from bit-mapped to bit-mapped creating a similar image
    • G06T5/40Image enhancement or restoration, e.g. from bit-mapped to bit-mapped creating a similar image by the use of histogram techniques
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • G06T7/0012Biomedical image inspection
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/12Edge-based segmentation
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/194Segmentation; Edge detection involving foreground-background segmentation
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10116X-ray image
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30004Biomedical image processing
    • G06T2207/30008Bone

Abstract

Locating the region of interest (ROI) in the histogram of a digital radiographic image is a key component for the optimized presentation of the image, either in hardcopy or softcopy display. A method for locating the ROI first locates key candidate landmarks present in a particular body part radiographic image (i.e., chest pelvis, hand, etc.). Next, a library of spatially located landmarks are matched to the candidate landmarks and used to locate the region of interest in the radiograph using geometric techniques. The histogram of the selected region of interest is used to develop the final tonescale curve used to process the image.

Description

FIELD OF THE INVENTION

This invention relates in general to digital image processing, and more specifically relates to a method for finding the region of interest that is used to develop the final tonescale curve for processing an image.

BACKGROUND OF THE INVENTION

In medical imaging, accurate diagnosis depends on the optimal presentation of the image, either on hardcopy or softcopy display. The optimal presentation will allow the radiologist to observe and detect small abnormalities that may not be visible in a presentation that is less than optimal.

In conventional screen/film radiography, the tonescale curve is built into the film as a function of the emulsion developed by the film manufacturer. The chemical development of the film also affects the final image visible on the film. Different films are available from manufactures to obtain "different looks" on the film.

The process of digitizing a film or obtaining the image by digital means, either storage phosphor or direct digital techniques, separates the acquisition step from the imaging processing steps used to obtain the final image. This separation allows an arbitrary tonescale curve to be used to obtain the final look of the image.

The purpose of the tonescale curve is to map the relevant code values obtained from either the digitization process or the direct digital acquisition to the final range of code values that will result in an optimal image presentation in some sense. Typically, this would not be a one to one mapping, and certain ranges of code values would be allocated more dynamic range than other code values in the final rendered image.

A common approach to find the region of interest is to analyze the code value histogram. This method works best when the peaks in the histogram corresponding to the region of interest are separated from the undesired regions. If the regions overlap, it becomes more difficult to find the region based on the analysis of the histogram only. Goodenough et al., U.S. Pat. No. 5,068,788, issued Nov. 26, 1991; Namiki et al., U.S. Pat. No. 5,198,669, issued Mar. 3, 1993; Doi et al., U.S. Pat. No. 4,839,807, issued 4,839,807, issued Jun. 13, 1989; Gouge, U.S. Pat. No. 5,040,225, issued Aug. 13, 1991; Shimura, U.S. Pat. No. 4,914,295, issued Apr. 3, 1990; Tanaka, U.S. Pat. No. 4,952,805, issued Aug. 28, 1990, are all histogram based techniques that do not solve this problem.

A method has been proposed by several researchers to obtain an optimal image by first segmenting the body part from foreground and background regions and then performing a histogram analysis on the remaining segmented image (Capozzi and Schaetzing, issued Nov. 17, 1992, U.S. Pat. No. 5,164,993; Jang and Schaetzing, issued Dec. 7, 1993, U.S. Pat. No. 5,268,967). These techniques require successful separation of the body part from the foreground and background.

A method based on the texture analysis of the image is described by Gaborsid, et al., U.S. Pat. No. 5,426,684, issued Jun. 20, 1995. Although this method overcomes some of the short comings of analyzing the code value histogram itself, the method requires substantial computer time to calculate the texture features.

All of these techniques find the tonescale curve based on either global code values or global bone and tissue regions. None of the methods use spatially located regions of interest.

SUMMARY OF THE INVENTION

According to a feature of the present invention, there is provided a solution to the problem of finding the corresponding code values of the region of interest using landmark feature locations combined with a geometric region of interest generation method.

According to a feature of the present invention, there is provided a method for finding the histogram region of interest of a digital radiographic image comprising the steps of: providing a digital radiographic image; applying edge detection to the provided image; applying a thresholding operation to the edge data to detect strong edges and remove weaker edges; performing a connected component analysis; detecting features; matching the detected features with features stored in a library of spatially referenced landmarks; mapping the region of interest information stored in the library onto the image; producing a histogram of the mapped region of interest; generating a tonescale look-up-table; and processing the image through the tonescale look-up-table to generate a tonescaled image.

ADVANTAGEOUS EFFECT OF THE INVENTION

The invention provides a method to spatially find the region of interest. This is a significant improvement over previous methods which depend on error prone histogram peak and valley finding techniques which do not provide spatial information and could provide erroneous results if segmentation failed, or if the shape of the histogram was different from what was expected. This might be due to patient positioning, objects in the background, or radiation backscatter which would cause activity in the foreground regions, among other reasons.

The texture based technique requires significant computer computation to calculate the feature values. Additionally, this method sorts the code values for all the bone and tissue regions in the image into two groups. It does not provide the spatial location of the region of interest, such as the vertebrae in a c-spine image. In a c-spine image, the bone histogram would include the vertebrae bone code values, but would also include skull and shoulder bone code values. The image that results from applying the tonescale which was determined from these code values is less than optimal. Also, if the region of interest contains both bone and tissue regions, this method is ineffective.

The method of the invention provides a robust tonescale algorithm.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a block diagram of the imaging system in which the method of the present invention can be practiced.

FIG. 2 is a block diagram showing the steps of the invention.

FIG. 3 is a diagrammatic view of an example of a gray level radiograph.

FIG. 4 is a diagrammatic view of an example of an edge map that was generated by using a gradient edge operator.

FIG. 5 is a diagrammatic view of a thresholded edge map.

FIG. 6 is a diagrammatic view showing the result of applying a connected component operation to the thresholded edge map and discarding the short connected components.

FIGS. 7a and 7b are graphical views of an example of the connected component data values and the conic curve derived from this data.

FIG. 8 represents a table in which the landmark and region of interest is stored.

FIGS. 9a-9c are diagrammatic views illustrating the structure for the Library of Spatially Referenced Landmarks.

FIGS. 10a and 10b are diagrammatic views illustrating geometric transformation of the ROI.

FIG. 11 is a block diagram of a digital imaging processor for carrying out the invention.

DETAILED DESCRIPTION OF THE INVENTION

FIG. 1 illustrates a typical system in which the described invention can be practiced. The system 10 includes input image 12, image acquisition system 14 (such as a projection radiography, MRI, CT, ultrasound system, or film digitizer), and digital image processing system 16 processes the digital image data according to the method of the invention to obtain an optimal representation of the data for presentation. The processed image could then be displayed on a softcopy device 18 or printed on a film or paper media in the output image block 20.

The digital image is processed in image processor 16, according to the method of the present invention. Image processor 16 can take the form of a digital computer, such as illustrated in FIG. 11. In such case, one or more of the steps of said method can be carried out using software routines. Image processor can also include hardware or firmware for carrying out one or more of said method steps. Thus, the steps of the method of the invention can be carried out using software, firmware, and hardware, either alone or in any preferable combination.

As shown in FIG. 11, a digital computer 300 includes a memory 310 for storing digital images, application programs, operating system, etc. Memory 310 can include mass memory (such as a hard magnetic disc or CD ROM), and fast memory (such as RAM). Computer 300 also includes input device 312 (such as a keyboard, mouse, touch screen), display 314 (CRT monitor, LCD), central processing unit 316 (microprocessor), output device 318 (thermal printer, dot matrix printer, laser printer, inkjet printer). Components 310,312,314,316,318 are connected together by control/data bus 320. Computer 300 can include a transportable storage medium drive 322 for reading from and/or writing to transportable storage media 324, such as a floppy magnetic disk or writeable optical compact disk (CD).

As used in this application, computer readable storage medium can include, specifically, memory 310 and transportable storage medium 324. More generally, computer storage medium may comprise, for example, magnetic storage media, such as magnetic disk (hard drive, floppy disk) or magnetic tape; optical storage media, such as optical disk, optical tape, or machine readable bar code; solid state electronic storage devices, such as random access memory (RAM), read only memory (ROM); or any other physical device or medium which can be employed to store a computer program.

FIG. 2 illustrates the method of the present invention.

Box 201 is the original gray level digital radiographic image (such as shown in FIG. 3).

An edge detection algorithm, such as a Sobel, Laplacian, Robert's operator [Reference: Digital Image Processing, William Pratt, Wiley-International, 1991, Chapter 16, Edge Detection] is applied in Box 205. The result is illustrated in FIG. 4. Next, a thresholding operation is applied to the edge data to detect strong edges and remove the weaker edges. The result is illustrated in FIG. 5.

A Connected Component Analysis using a chain code is performed in 210 (FIG. 2) [Reference: Computer Vision, Ballard and Brown, Prentice-Hall, 1982, p. 235-237]. A connected component is a connected series of pixels. Each pixel has a corresponding x and y value. The connected components arm rank ordered by length, and the shorter components are discarded. The result is illustrated in FIG. 6.

The remaining connected components are used to define the shape features (FIG. 2, Box 220). Several methods can be used to represent the shape features. The chain code used to represent the connected components can be used as features themselves, straight line segments can be used to approximate the curve segments, or a higher level representation, such as analytic functions could be used. An example of such a function is a conic. FIGS. 7a and 7b illustrate this method. A least squares fit to a generalized conic is used to determine the coefficients of the conic that best matches the connected component values [Reference: "A note on the least squares fitting of ellipses," Paul L. Rosin, Pattern Recognition Letters, Vol. 14, 1993, p. 799-808].

The characteristics of this conic (coefficients, orientation, resulting error of fit, etc.) are used as features that are matched to the Library of Spatially Referenced Features (Box 225, FIG. 2). The Body Part Information (Box 215) is used as an index to the library to locate the correct stored feature values and ROI (FIG. 8).

The feature values stored in the library 225 are determined by extracting the features from a large number of labeled images with known regions of interests during a training phase. The landmarks are represented by mean values and a variance. In addition to the key feature locations stored in the Library of Spatially Referenced Features 225, a region of interest (ROI) is geometrically defined by reference to the landmarks. The ROI is an area in the image defined to contain the significant diagnosis information. This region may or may not contain the detected landmarks, but is geometrically referenced to those landmarks. In one class of images, the ROI may be defined as a convex hull surrounding the features, but in another image class, the region of interest might be described as a region that is somehow related geometrically to the landmarks, such as above, below, to the right of, between two landmarks, etc.

Once the features from the image under evaluation and the stored landmarks are matched, the ROI information stored in the library will be mapped onto the image under investigation (Box 230). It is not necessary to match every feature in the reference library. FIGS. 9a-9c illustrate an example of key edges that would be represented by features for a image.

In Box 230 (FIG. 2), a matching metric is used to determine the best match between the features of the image under evaluation and the stored features in the Library of Spatially Referenced Features (Box 225). The image under evaluation may have fewer or more features that the features in the library. The key objective is to find a set of matching features that can be used as landmarks to determine the region of interest as defined in the library. A goodness metric is used to determine the match. One possible goodness metric would be to sum the number of matching features between the image under evaluation and the features stored in the library. The features may be weighted, that is, certain features that are judged to be detected more reliably than others would carry a higher weight. This will bias the goodness metric to favor robust features that which are reliably detected. It is also not necessary to have a perfect feature match. In addition to an exact location for a given feature, and specific characteristics for that feature, a range of locations and features are acceptable. For example, if a parabola of size 32 pixels with an orientation of north is defined in the library, a matching feature would be a parabola of size 32 pixels plus or minus some delta, with an orientation of north, plus or minus k degrees, where k is a constant value that was determined through experimentation with a large set of images. The variations from the data stored in the library would be used to determine the correct ROI on the image (FIG. 10).

The histogram of the data in the image under evaluation that corresponds to the transformed ROI (FIG. 2, Box 240) would be used to generate the tonescale curve.

This curve, in the form of a look-up-table, LUT, (FIG. 2, Box 250) would be used to map the gray level values of the pixels in the image to generate the tonescaled image (FIG. 2, Box 255).

The invention has been described in detail with particular reference to certain preferred embodiments thereof, but it will be understood that variations and modifications can be effected within the spirit and scope of the invention.

PARTS LIST

10 system

12 input image

14 image acquisition system

16 image processor

18 softcopy device

20 output image block

201 gray level image

205 edge detection and thresholding

210 connected component analysis

215 body part information

220 feature detection

225 Library of Spatially Referenced Landmarks

230 feature matching

235 region of interest for body part

240 histogram of region of interest

245 generation of tonescale LUT

250 apply LUT

255 tonescaled image

300 digital computer

310 memory

312 input device

314 display

316 central processing unit

318 output device

320 control/data bus

322 transportable storage medium drive

324 transportable storage medium

Claims (8)

What is claimed is:
1. A method for finding the histogram region of interest of a digital radiographic image comprising the steps of:
providing a digital radiographic image;
applying edge detection to said provided image;
applying a thresholding operation to the edge data to detect strong edges and remove weaker edges;
performing a connected component analysis;
detecting spatial features;
matching the detected spatial features with spatial features stored in a library of spatially referenced landmarks of unique body parts;
mapping the region of interest information stored in said library onto said image;
producing a histogram of said mapped region of interest;
generating a tonescale look-up-table; and
processing said image through said tonescale look-up-table to generate a tonescaled image.
2. The method of claim 1 wherein said applying step applies an edge detection algorithm, such as a Sobel, Laplacian, or Robert's operator.
3. The method of claim 1 wherein said performing step includes rank ordering connected components by length and discarding components with length less than database threshold, "T".
4. The method of claim 1 wherein said detecting features step includes one or more of the following: the chain code used to represent the connected components is used as features themselves, straight line segments are used to approximate curve segments, analytic functions are used such as a least squares fit to a generalized conic with characteristics of the conic (coefficients, orientation, resulting error of fit) used as features.
5. The method of claim 1 wherein said matching step includes using a goodness metric.
6. The method of claim 5 wherein said goodness metric is the sum of the number of matching features between the image under evaluation and the features stored in said library.
7. The method of claim 6 wherein said features are weighted so that features judged to be detected more reliably than others carry a higher weight.
8. A computer storage produce comprising:
a computer readable storage medium storing a computer program for carrying out a method for finding the histogram region of interest of a digital radiographic image comprising the steps of:
providing a digital radiographic image;
applying edge detection to said provided image;
applying a thresholding operation to the edge data to detect strong edges and remove weaker edges;
performing a connected component analysis;
detecting shape features;
matching the detected shape features with features stored in a library of spatially referenced landmarks of unique body parts;
mapping the region of interest information stored in said library onto said image;
producing a histogram of said mapped region of interest;
generating a tonescale look-up-table; and
processing said image through said tonescale look-up-table to generate a tonescaled image.
US08946557 1997-10-07 1997-10-07 Technique for finding the histogram region of interest based on landmark detection for improved tonescale reproduction of digital radiographic images Expired - Lifetime US6018590A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US08946557 US6018590A (en) 1997-10-07 1997-10-07 Technique for finding the histogram region of interest based on landmark detection for improved tonescale reproduction of digital radiographic images

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US08946557 US6018590A (en) 1997-10-07 1997-10-07 Technique for finding the histogram region of interest based on landmark detection for improved tonescale reproduction of digital radiographic images

Publications (1)

Publication Number Publication Date
US6018590A true US6018590A (en) 2000-01-25

Family

ID=25484653

Family Applications (1)

Application Number Title Priority Date Filing Date
US08946557 Expired - Lifetime US6018590A (en) 1997-10-07 1997-10-07 Technique for finding the histogram region of interest based on landmark detection for improved tonescale reproduction of digital radiographic images

Country Status (1)

Country Link
US (1) US6018590A (en)

Cited By (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6118892A (en) * 1998-11-19 2000-09-12 Direct Radiography Corp. Method for automatic detection of region of interest for digital x-ray detectors using a filtered histogram
US6215893B1 (en) * 1998-05-24 2001-04-10 Romedix Ltd. Apparatus and method for measurement and temporal comparison of skin surface images
WO2001060237A2 (en) * 2000-02-18 2001-08-23 Robert Kenet Method and device for skin cancer screening
WO2002094098A1 (en) * 2001-05-18 2002-11-28 Polartechnics Limited Diagnostic feature extraction in dermatological examination
US6507670B1 (en) * 1998-03-05 2003-01-14 Ncr Corporation System and process for removing a background pattern from a binary image
US6694047B1 (en) * 1999-07-15 2004-02-17 General Electric Company Method and apparatus for automated image quality evaluation of X-ray systems using any of multiple phantoms
US20040037473A1 (en) * 2002-08-20 2004-02-26 Ahmed Mohamed N. Systems and methods for content-based document image enhancement
US20060039690A1 (en) * 2004-08-16 2006-02-23 Eran Steinberg Foreground/background segmentation in digital images with differential exposure calculations
US20060074312A1 (en) * 2004-10-06 2006-04-06 Bogdan Georgescu Medical diagnostic ultrasound signal extraction
US20060126093A1 (en) * 2004-12-09 2006-06-15 Fedorovskaya Elena A Method for automatically determining the acceptability of a digital image
US20070127813A1 (en) * 2005-12-01 2007-06-07 Shesha Shah Approach for near duplicate image detection
US20070147820A1 (en) * 2005-12-27 2007-06-28 Eran Steinberg Digital image acquisition system with portrait mode
US20070189602A1 (en) * 2006-02-07 2007-08-16 Siemens Medical Solutions Usa, Inc. System and Method for Multiple Instance Learning for Computer Aided Detection
US20070250548A1 (en) * 2006-04-21 2007-10-25 Beckman Coulter, Inc. Systems and methods for displaying a cellular abnormality
US20070269108A1 (en) * 2006-05-03 2007-11-22 Fotonation Vision Limited Foreground / Background Separation in Digital Images
US20080170765A1 (en) * 2005-04-25 2008-07-17 Koninklijke Philips Electronics, N.V. Targeted Additive Gain Tool For Processing Ultrasound Images
US20080187213A1 (en) * 2007-02-06 2008-08-07 Microsoft Corporation Fast Landmark Detection Using Regression Methods
US20090040342A1 (en) * 2006-02-14 2009-02-12 Fotonation Vision Limited Image Blurring
US20090066971A1 (en) * 2007-09-06 2009-03-12 Ali Zandifar Characterization of a Printed Droplet
US20090273685A1 (en) * 2006-02-14 2009-11-05 Fotonation Vision Limited Foreground/Background Segmentation in Digital Images
US20090279778A1 (en) * 2006-06-23 2009-11-12 Koninklijke Philips Electronics N.V. Method, a system and a computer program for determining a threshold in an image comprising image values
US7680342B2 (en) 2004-08-16 2010-03-16 Fotonation Vision Limited Indoor/outdoor classification in digital images
US7805003B1 (en) * 2003-11-18 2010-09-28 Adobe Systems Incorporated Identifying one or more objects within an image
EP2854385A1 (en) * 2013-09-26 2015-04-01 Kyocera Document Solutions Inc. Image forming apparatus and image forming method

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4839807A (en) * 1987-08-03 1989-06-13 University Of Chicago Method and system for automated classification of distinction between normal lungs and abnormal lungs with interstitial disease in digital chest radiographs
US4914295A (en) * 1985-06-25 1990-04-03 Fuji Photo Film Co., Ltd. Radiation image read-out and image signal storing apparatus
US4952805A (en) * 1987-08-20 1990-08-28 Fuji Photo Film Co., Ltd. Method of judging the presence or absence of a limited irradiation field, method of selecting a correct irradiation field, and method of judging correctness or incorrectness of an irradiation field
US5040225A (en) * 1987-12-07 1991-08-13 Gdp, Inc. Image analysis method
US5068788A (en) * 1988-11-29 1991-11-26 Columbia Scientific Inc. Quantitative computed tomography system
US5164993A (en) * 1991-11-25 1992-11-17 Eastman Kodak Company Method and apparatus for automatic tonescale generation in digital radiographic images
US5198669A (en) * 1989-09-20 1993-03-30 Fujitsu Limited Digital X-ray image processing apparatus
US5268967A (en) * 1992-06-29 1993-12-07 Eastman Kodak Company Method for automatic foreground and background detection in digital radiographic images
US5426684A (en) * 1993-11-15 1995-06-20 Eastman Kodak Company Technique for finding the histogram region of interest for improved tone scale reproduction of digital radiographic images

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4914295A (en) * 1985-06-25 1990-04-03 Fuji Photo Film Co., Ltd. Radiation image read-out and image signal storing apparatus
US4839807A (en) * 1987-08-03 1989-06-13 University Of Chicago Method and system for automated classification of distinction between normal lungs and abnormal lungs with interstitial disease in digital chest radiographs
US4952805A (en) * 1987-08-20 1990-08-28 Fuji Photo Film Co., Ltd. Method of judging the presence or absence of a limited irradiation field, method of selecting a correct irradiation field, and method of judging correctness or incorrectness of an irradiation field
US5040225A (en) * 1987-12-07 1991-08-13 Gdp, Inc. Image analysis method
US5068788A (en) * 1988-11-29 1991-11-26 Columbia Scientific Inc. Quantitative computed tomography system
US5198669A (en) * 1989-09-20 1993-03-30 Fujitsu Limited Digital X-ray image processing apparatus
US5164993A (en) * 1991-11-25 1992-11-17 Eastman Kodak Company Method and apparatus for automatic tonescale generation in digital radiographic images
US5268967A (en) * 1992-06-29 1993-12-07 Eastman Kodak Company Method for automatic foreground and background detection in digital radiographic images
US5426684A (en) * 1993-11-15 1995-06-20 Eastman Kodak Company Technique for finding the histogram region of interest for improved tone scale reproduction of digital radiographic images

Cited By (51)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6507670B1 (en) * 1998-03-05 2003-01-14 Ncr Corporation System and process for removing a background pattern from a binary image
US6215893B1 (en) * 1998-05-24 2001-04-10 Romedix Ltd. Apparatus and method for measurement and temporal comparison of skin surface images
US6118892A (en) * 1998-11-19 2000-09-12 Direct Radiography Corp. Method for automatic detection of region of interest for digital x-ray detectors using a filtered histogram
US6694047B1 (en) * 1999-07-15 2004-02-17 General Electric Company Method and apparatus for automated image quality evaluation of X-ray systems using any of multiple phantoms
WO2001060237A2 (en) * 2000-02-18 2001-08-23 Robert Kenet Method and device for skin cancer screening
US7522825B2 (en) 2000-02-18 2009-04-21 Robert Kenet Method and device for skin cancer screening
WO2001060237A3 (en) * 2000-02-18 2004-02-12 Robert Kenet Method and device for skin cancer screening
US20040258288A1 (en) * 2000-02-18 2004-12-23 Robert Kenet Method and device for skin cancer screening
WO2002094098A1 (en) * 2001-05-18 2002-11-28 Polartechnics Limited Diagnostic feature extraction in dermatological examination
US20040037473A1 (en) * 2002-08-20 2004-02-26 Ahmed Mohamed N. Systems and methods for content-based document image enhancement
US7079686B2 (en) 2002-08-20 2006-07-18 Lexmark International, Inc. Systems and methods for content-based document image enhancement
US7805003B1 (en) * 2003-11-18 2010-09-28 Adobe Systems Incorporated Identifying one or more objects within an image
US7606417B2 (en) 2004-08-16 2009-10-20 Fotonation Vision Limited Foreground/background segmentation in digital images with differential exposure calculations
US20060039690A1 (en) * 2004-08-16 2006-02-23 Eran Steinberg Foreground/background segmentation in digital images with differential exposure calculations
US8175385B2 (en) 2004-08-16 2012-05-08 DigitalOptics Corporation Europe Limited Foreground/background segmentation in digital images with differential exposure calculations
US20110025859A1 (en) * 2004-08-16 2011-02-03 Tessera Technologies Ireland Limited Foreground/Background Segmentation in Digital Images
US20110157408A1 (en) * 2004-08-16 2011-06-30 Tessera Technologies Ireland Limited Foreground/Background Segmentation in Digital Images with Differential Exposure Calculations
US7957597B2 (en) 2004-08-16 2011-06-07 Tessera Technologies Ireland Limited Foreground/background segmentation in digital images
US7912285B2 (en) 2004-08-16 2011-03-22 Tessera Technologies Ireland Limited Foreground/background segmentation in digital images with differential exposure calculations
US7680342B2 (en) 2004-08-16 2010-03-16 Fotonation Vision Limited Indoor/outdoor classification in digital images
US20060074312A1 (en) * 2004-10-06 2006-04-06 Bogdan Georgescu Medical diagnostic ultrasound signal extraction
WO2006041548A1 (en) * 2004-10-06 2006-04-20 Siemens Medical Solutions Usa, Inc. Ultrasound signal extraction from medical ultrtasound images
US7899256B2 (en) * 2004-12-09 2011-03-01 Eastman Kodak Company Method for automatically determining the acceptability of a digital image
US20100303363A1 (en) * 2004-12-09 2010-12-02 Fedorovskaya Elena A Method for automatically determining the acceptability of a digital image
US7809197B2 (en) * 2004-12-09 2010-10-05 Eastman Kodak Company Method for automatically determining the acceptability of a digital image
US20060126093A1 (en) * 2004-12-09 2006-06-15 Fedorovskaya Elena A Method for automatically determining the acceptability of a digital image
US20080170765A1 (en) * 2005-04-25 2008-07-17 Koninklijke Philips Electronics, N.V. Targeted Additive Gain Tool For Processing Ultrasound Images
US7860308B2 (en) * 2005-12-01 2010-12-28 Yahoo! Inc. Approach for near duplicate image detection
US20070127813A1 (en) * 2005-12-01 2007-06-07 Shesha Shah Approach for near duplicate image detection
US7692696B2 (en) 2005-12-27 2010-04-06 Fotonation Vision Limited Digital image acquisition system with portrait mode
US20100182458A1 (en) * 2005-12-27 2010-07-22 Fotonation Ireland Limited Digital image acquisition system with portrait mode
US8212897B2 (en) 2005-12-27 2012-07-03 DigitalOptics Corporation Europe Limited Digital image acquisition system with portrait mode
US20070147820A1 (en) * 2005-12-27 2007-06-28 Eran Steinberg Digital image acquisition system with portrait mode
US7986827B2 (en) * 2006-02-07 2011-07-26 Siemens Medical Solutions Usa, Inc. System and method for multiple instance learning for computer aided detection
US20070189602A1 (en) * 2006-02-07 2007-08-16 Siemens Medical Solutions Usa, Inc. System and Method for Multiple Instance Learning for Computer Aided Detection
US20110102628A1 (en) * 2006-02-14 2011-05-05 Tessera Technologies Ireland Limited Foreground/Background Segmentation in Digital Images
US7953287B2 (en) 2006-02-14 2011-05-31 Tessera Technologies Ireland Limited Image blurring
US20090273685A1 (en) * 2006-02-14 2009-11-05 Fotonation Vision Limited Foreground/Background Segmentation in Digital Images
US7868922B2 (en) 2006-02-14 2011-01-11 Tessera Technologies Ireland Limited Foreground/background segmentation in digital images
US20090040342A1 (en) * 2006-02-14 2009-02-12 Fotonation Vision Limited Image Blurring
US20070250548A1 (en) * 2006-04-21 2007-10-25 Beckman Coulter, Inc. Systems and methods for displaying a cellular abnormality
US8358841B2 (en) 2006-05-03 2013-01-22 DigitalOptics Corporation Europe Limited Foreground/background separation in digital images
US20100329549A1 (en) * 2006-05-03 2010-12-30 Tessera Technologies Ireland Limited Foreground/Background Separation in Digital Images
US8363908B2 (en) * 2006-05-03 2013-01-29 DigitalOptics Corporation Europe Limited Foreground / background separation in digital images
US9117282B2 (en) 2006-05-03 2015-08-25 Fotonation Limited Foreground / background separation in digital images
US20070269108A1 (en) * 2006-05-03 2007-11-22 Fotonation Vision Limited Foreground / Background Separation in Digital Images
US20090279778A1 (en) * 2006-06-23 2009-11-12 Koninklijke Philips Electronics N.V. Method, a system and a computer program for determining a threshold in an image comprising image values
US20080187213A1 (en) * 2007-02-06 2008-08-07 Microsoft Corporation Fast Landmark Detection Using Regression Methods
US20090066971A1 (en) * 2007-09-06 2009-03-12 Ali Zandifar Characterization of a Printed Droplet
US7783107B2 (en) * 2007-09-06 2010-08-24 Seiko Epson Corporation Characterization of a printed droplet
EP2854385A1 (en) * 2013-09-26 2015-04-01 Kyocera Document Solutions Inc. Image forming apparatus and image forming method

Similar Documents

Publication Publication Date Title
Ferrari et al. Automatic identification of the pectoral muscle in mammograms
Goldszal et al. An image-processing system for qualitative and quantitative volumetric analysis of brain images
Sandor et al. Surface-based labeling of cortical anatomy using a deformable atlas
Lu et al. Detection of incomplete ellipse in images with strong noise by iterative randomized Hough transform (IRHT)
Brown et al. Registration of planar film radiographs with computed tomography
Liu et al. Robust midsagittal plane extraction from normal and pathological 3-D neuroradiology images
US7876938B2 (en) System and method for whole body landmark detection, segmentation and change quantification in digital images
US5268967A (en) Method for automatic foreground and background detection in digital radiographic images
US6728424B1 (en) Imaging registration system and method using likelihood maximization
US6359960B1 (en) Method for identifying and locating markers in a 3D volume data set
US6697506B1 (en) Mark-free computer-assisted diagnosis method and system for assisting diagnosis of abnormalities in digital medical images using diagnosis based image enhancement
US5579360A (en) Mass detection by computer using digital mammograms of the same breast taken from different viewing directions
Studholme et al. Automated 3-D registration of MR and CT images of the head
US5457754A (en) Method for automatic contour extraction of a cardiac image
US6404936B1 (en) Subject image extraction method and apparatus
Klinder et al. Automated model-based vertebra detection, identification, and segmentation in CT images
US6282307B1 (en) Method and system for the automated delineation of lung regions and costophrenic angles in chest radiographs
Mattes et al. Nonrigid multimodality image registration
Collins et al. Model-based segmentation of individual brain structures from MRI data
US7298881B2 (en) Method, system, and computer software product for feature-based correlation of lesions from multiple images
Van den Elsen et al. Automatic registration of CT and MR brain images using correlation of geometrical features
van Herk et al. Automatic three‐dimensional correlation of CT‐CT, CT‐MRI, and CT‐SPECT using chamfer matching
US20070242869A1 (en) Processing and measuring the spine in radiographs
US5799099A (en) Automatic technique for localizing externally attached fiducial markers in volume images of the head
US20020009215A1 (en) Automated method and system for the segmentation of lung regions in computed tomography scans

Legal Events

Date Code Title Description
AS Assignment

Owner name: EASTMAN KODAK COMPANY, NEW YORK

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:GABORSKI, ROGER S.;REEL/FRAME:008767/0043

Effective date: 19971007

FPAY Fee payment

Year of fee payment: 4

FPAY Fee payment

Year of fee payment: 8

AS Assignment

Owner name: CREDIT SUISSE, CAYMAN ISLANDS BRANCH, AS ADMINISTR

Free format text: FIRST LIEN OF INTELLECTUAL PROPERTY SECURITY AGREEMENT;ASSIGNOR:CARESTREAM HEALTH, INC.;REEL/FRAME:019649/0454

Effective date: 20070430

Owner name: CREDIT SUISSE, CAYMAN ISLANDS BRANCH, AS ADMINISTR

Free format text: SECOND LIEN INTELLECTUAL PROPERTY SECURITY AGREEME;ASSIGNOR:CARESTREAM HEALTH, INC.;REEL/FRAME:019773/0319

Effective date: 20070430

AS Assignment

Owner name: CARESTREAM HEALTH, INC., NEW YORK

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:EASTMAN KODAK COMPANY;REEL/FRAME:020741/0126

Effective date: 20070501

Owner name: CARESTREAM HEALTH, INC., NEW YORK

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:EASTMAN KODAK COMPANY;REEL/FRAME:020756/0500

Effective date: 20070501

Owner name: CARESTREAM HEALTH, INC.,NEW YORK

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:EASTMAN KODAK COMPANY;REEL/FRAME:020741/0126

Effective date: 20070501

Owner name: CARESTREAM HEALTH, INC.,NEW YORK

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:EASTMAN KODAK COMPANY;REEL/FRAME:020756/0500

Effective date: 20070501

AS Assignment

Owner name: CARESTREAM HEALTH, INC., NEW YORK

Free format text: RELEASE OF SECURITY INTEREST IN INTELLECTUAL PROPERTY (FIRST LIEN);ASSIGNOR:CREDIT SUISSE AG, CAYMAN ISLANDS BRANCH;REEL/FRAME:026069/0012

Effective date: 20110225

AS Assignment

Owner name: CREDIT SUISSE AG, CAYMAN ISLANDS BRANCH, NEW YORK

Free format text: INTELLECTUAL PROPERTY SECURITY AGREEMENT;ASSIGNORS:CARESTREAM HEALTH, INC.;CARESTREAM DENTAL, LLC;QUANTUM MEDICAL IMAGING, L.L.C.;AND OTHERS;REEL/FRAME:026269/0411

Effective date: 20110225

FPAY Fee payment

Year of fee payment: 12

AS Assignment

Owner name: CARESTREAM HEALTH, INC., NEW YORK

Free format text: RELEASE OF SECURITY INTEREST IN INTELLECTUAL PROPERTY (SECOND LIEN);ASSIGNOR:CREDIT SUISSE AG, CAYMAN ISLANDS BRANCH;REEL/FRAME:027851/0812

Effective date: 20110225

AS Assignment

Owner name: CREDIT SUISSE AG, CAYMAN ISLANDS BRANCH, NEW YORK

Free format text: AMENDED AND RESTATED INTELLECTUAL PROPERTY SECURITY AGREEMENT (FIRST LIEN);ASSIGNORS:CARESTREAM HEALTH, INC.;CARESTREAM DENTAL LLC;QUANTUM MEDICAL IMAGING, L.L.C.;AND OTHERS;REEL/FRAME:030711/0648

Effective date: 20130607

AS Assignment

Owner name: CREDIT SUISSE AG, CAYMAN ISLANDS BRANCH, NEW YORK

Free format text: SECOND LIEN INTELLECTUAL PROPERTY SECURITY AGREEMENT;ASSIGNORS:CARESTREAM HEALTH, INC.;CARESTREAM DENTAL LLC;QUANTUM MEDICAL IMAGING, L.L.C.;AND OTHERS;REEL/FRAME:030724/0154

Effective date: 20130607